#多線程實戰(zhàn)栗子（糗百）
#用一個隊列Queue對象，
#先產(chǎn)生所有url，put進隊列；
#開啟多線程，把queue隊列作為參數(shù)傳入
#主函數(shù)中讀取url
import requests
from queue import Queue
import re,os,threading,time
# 構(gòu)造所有ip地址并添加進queue隊列
headers = {
  'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36'
}
urlQueue = Queue()
[urlQueue.put('http://www.qiumeimei.com/image/page/{}'.format(i)) for i in range(1,14)]
def get_image(urlQueue):
  while True:
    try:
      # 不阻塞的讀取隊列數(shù)據(jù)
      url = urlQueue.get_nowait()
      # i = urlQueue.qsize()
    except Exception as e:
      break
    print('Current Thread Name %s, Url: %s ' % (threading.currentThread().name, url))
    try:
      res = requests.get(url, headers=headers)
      url_infos = re.findall('data-lazy-src="(.*?)"', res.text, re.S)
      for url_info in url_infos:
        if os.path.exists(img_path + url_info[-20:]):
          print('圖片已存在')
        else:
          image = requests.get(url_info, headers=headers)
          with open(img_path + url_info[-20:], 'wb') as fp:
            time.sleep(1)
            fp.write(image.content)
          print('正在下載:' + url_info)
    except Exception as e:
      print(e)
if __name__ == '__main__':
  startTime = time.time()
  # 定義圖片存儲路徑
  img_path = './img/'
  if not os.path.exists(img_path):
    os.mkdir(img_path)
  threads = []
  # 可以調(diào)節(jié)線程數(shù)， 進而控制抓取速度
  threadNum = 4
  for i in range(0, threadNum):
    t = threading.Thread(target=get_image, args=(urlQueue,))
    threads.append(t)
  for t in threads:
    t.start()
  for t in threads:
    # 多線程多join的情況下，依次執(zhí)行各線程的join方法, 這樣可以確保主線程最后退出， 且各個線程間沒有阻塞
    t.join()
  endTime = time.time()
  print('Done, Time cost: %s ' % (endTime - startTime))